bigcode/starcoder2-3b
22449k
1{2 "architectures": [3 "Starcoder2ForCausalLM"4 ],5 "attention_dropout": 0.1,6 "residual_dropout": 0.1,7 "embedding_dropout": 0.1,8 "bos_token_id": 0,9 "eos_token_id": 0,10 "hidden_act": "gelu_pytorch_tanh",11 "hidden_size": 3072,12 "initializer_range": 0.018042,13 "intermediate_size": 12288,14 "max_position_embeddings": 16384,15 "mlp_type": "default",16 "model_type": "starcoder2",17 "norm_epsilon": 1e-05,18 "norm_type": "layer_norm",19 "num_attention_heads": 24,20 "num_hidden_layers": 30,21 "num_key_value_heads": 2,22 "rope_theta": 999999.4420358813,23 "sliding_window": 4096,24 "transformers_version": "4.37.0.dev0",25 "use_bias": true,26 "use_cache": true,27 "vocab_size": 4915228}29 